论文部分内容阅读
由于R&D活动的高风险性,对国防R&D项目开展中止决策研究具有重要的理论和现实意义.将传统R&D项目中止决策的解决途径分为两类:分类型和回归型.在分析这两种解决途径存在不足的情况下,考虑到国防R&D项目自身的特点,提出一种基于混合支持向量机(support vector machine,SVM)的项目中止决策方法;同时,针对模型的建立问题,提出采用交叉验证的方法,通过粒子群优化(particle swarm optimization,PSO)算法实现模型的优化选择.通过建立混合决策模型,可以得出项目中止决策的明确结论.应用分析表明,该方法能够同时实现对项目的分类和排序,较常用方法利用信息更为全面,得出结论更为细致,对实践中的项目中止决策具有较好的适应性.
Due to the high risk of R & D activities, it is of important theoretical and practical significance to carry out the study on the suspension decision-making of the national defense R & D project.There are two types of solutions to the termination of decision-making in the traditional R & D projects: classification and regression.In the analysis of the two solutions Considering the characteristics of the national defense R & D project, this paper proposes a project discontinuation decision-making method based on the support vector machine (SVM). At the same time, in view of the establishment of the model, this paper proposes a cross-validation Method to optimize the model through the particle swarm optimization (PSO) algorithm.By establishing a hybrid decision model, we can draw a clear conclusion of the project termination decision.Application analysis shows that this method can simultaneously achieve the classification of the project and Sort, more commonly used methods to use information more comprehensive, concluded that more detailed, practical termination of the project has a better adaptability.